app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "14maddy/Agrithm-llama-agriculture-chat-bot"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32)

def chat(message, history):
    prompt = f"### Instruction:\n{message}\n\n### Response:\n"
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(
        **inputs,
        max_new_tokens=200,
        temperature=0.4,
        repetition_penalty=1.35,
        do_sample=True
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    response = response.split("### Response:")[-1].strip()
    return response

demo = gr.ChatInterface(fn=chat, title="🌾 Agrithm — Kisan AI")
demo.launch()
```

**`requirements.txt`**
```
transformers
torch
gradio
accelerate